© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83165
    Prev
    Next
    INDEX
    Explanations

    night work

    np_acts-logits-general · gemini-2.5-flash-lite

    Extraction, see, pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    I
    0.58
     collisions
    0.51
     misog
    0.50
     hitched
    0.48
     transmis
    0.47
     Situs
    0.46
     FOOD
    0.46
     Malays
    0.45
     FRI
    0.45
     reactions
    0.45
    POSITIVE LOGITS
    賬
    0.60
     თუ
    0.53
    阠
    0.52
    颖
    0.50
     గ్ర
    0.49
     грудня
    0.48
    颗粒
    0.48
     держав
    0.47
     наблюда
    0.47
    创建一个
    0.47
    Activations Density 0.000%

    No Known Activations